Geoscientific Model Development
Geoscientific Model Development
GMD
Articles | Volume 19, issue 13
Articles | Volume 19, issue 13
https://doi.org/10.5194/gmd-19-6027-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-19-6027-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 19, issue 13
Methods for assessment of models
 | 
08 Jul 2026
Methods for assessment of models |  | 08 Jul 2026

A self-supervised precipitation forecast verification based on contrastive learning

Yanwen Wang, Shuwen Huang, Qian Li, Xuan Peng, Haoming Chen, Kefeng Zhu, Liwen Wang, and Sheng Li

Viewed

Total article views: 2,162 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
1,355 612 195 2,162 186 186 218
  • HTML: 1,355
  • PDF: 612
  • XML: 195
  • Total: 2,162
  • Supplement: 186
  • BibTeX: 186
  • EndNote: 218
Views and downloads (calculated since 23 Feb 2026)
Cumulative views and downloads (calculated since 23 Feb 2026)

Viewed (geographical distribution)

Total article views: 2,162 (including HTML, PDF, and XML) Thereof 2,054 with geography defined and 108 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Saved (final revised paper)

Latest update: 28 Oct 2026
Download
Short summary
We developed a contrastive learning method (CLPFV - contrastive learning-based precipitation forecast verification) to improve the accuracy of precipitation forecast verification. The proposed method uses precipitation augmentation to simulate real-world forecast errors with gradients and then employs an improved loss function to reflect these errors in the contrastive learning. Experimental results show that the proposed method outperforms traditional and spatial verification methods across different error types and aligns better with expert judgment.
Read more
Share
Altmetrics
Final-revised paper
Preprint